© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 649
    Prev
    Next
    INDEX
    Explanations

    New followed by places or things

    np_acts-logits-general · gemini-2.5-flash-lite

    new followed by type or void followed by function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    .
    1.03
    are
    0.72
    the
    0.71
    ↵
    0.71
    re
    0.69
    ate
    0.66
    that
    0.65
    ле
    0.63
    al
    0.61
    will
    0.61
    POSITIVE LOGITS
     at
    0.80
    ک
    0.76
    ਰ
    0.68
    تم
    0.67
     was
    0.66
    кою
    0.63
    کس
    0.61
    ０
    0.61
     باہر
    0.60
    م
    0.60
    Activations Density 0.123%

    No Known Activations